Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation

Documenti analoghi

• CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
  di: Poppi, Tobia, et al.
  Pubblicazione: (2026)
• Learning to Rank Caption Chains for Video-Text Alignment
  di: Blume, Ansel, et al.
  Pubblicazione: (2026)
• Object-Centric Vision Token Pruning for Vision Language Models
  di: Li, Guangyuan, et al.
  Pubblicazione: (2025)
• Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
  di: Wang, Weixing, et al.
  Pubblicazione: (2025)
• Dynamic Token Reduction during Generation for Vision Language Models
  di: Liang, Xiaoyu, et al.
  Pubblicazione: (2025)